Training in progress, step 500

config.json

@@ -8,7 +8,7 @@
   "classifier_dropout": 0.1,
   "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.4,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d943a4def3da6c20a9aeb9f62ec06cdb7050562ef534319622f0d25467b2306
+oid sha256:7820f347b0fb47f897fc22e730b858fce3e0125419ddee07860e09e574242c46
 size 1421587189

runs/Jul11_12-40-38_fb248a4130df/events.out.tfevents.1689079602.fb248a4130df.391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076b013bc63a209785c8946d7896374db5472b4e9092f720d89778a3b8262aca
+size 4688

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 300,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5a4b9e3dcbb90d331d933e74fa17e255325ae5d07b3fea82d0ecc6a815dc94
+oid sha256:cd97cb6fb3c4727c8d1e569bdb075bcd32015e22040a592529ba2ec0b7569728
 size 4027